Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19573
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Ani" with varying degrees of emphasis or relevance

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific character or entity throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alion
    -0.89
    nesday
    -0.89
    anwhile
    -0.80
    spin
    -0.79
    é¾įå¥ij士
    -0.77
    rique
    -0.76
    rified
    -0.75
    */(
    -0.72
    owship
    -0.72
    rious
    -0.72
    POSITIVE LOGITS
    emi
    1.42
    yah
    1.13
    Äĩ
    0.99
    ya
    0.94
    acs
    0.92
    orno
    0.90
    ZI
    0.88
    yy
    0.88
    wa
    0.87
    elson
    0.85
    Activations Density 0.015%

    No Known Activations